Mark K. Ho

Dilip Arumugam, Mark K. Ho, Noah D. Goodman et al. · stanford

Throughout the cognitive-science literature, there is widespread agreement that decision-making agents operating in the real world do so under limited information-processing capabilities and without access to unbounded cognitive or computational resources. Prior work has drawn inspiration from this fact and leveraged an information-theoretic model of such behaviors or policies as communication channels operating under a bounded rate constraint. Meanwhile, a parallel line of work also capitalizes on the same principles from rate-distortion theory to formalize capacity-limited decision making through the notion of a learning target, which facilitates Bayesian regret bounds for provably-efficient learning algorithms. In this paper, we aim to elucidate this latter perspective by presenting a brief survey of these information-theoretic models of capacity-limited decision making in biological and artificial agents.

Carlos G. Correa, Mark K. Ho, Frederick Callaway et al.

Human behavior emerges from planning over elaborate decompositions of tasks into goals, subgoals, and low-level actions. How are these decompositions created and used? Here, we propose and evaluate a normative framework for task decomposition based on the simple idea that people decompose tasks to reduce the overall cost of planning while maintaining task performance. Analyzing 11,117 distinct graph-structured planning tasks, we find that our framework justifies several existing heuristics for task decomposition and makes predictions that can be distinguished from two alternative normative accounts. We report a behavioral study of task decomposition ($N=806$) that uses 30 randomly sampled graphs, a larger and more diverse set than that of any previous behavioral study on this topic. We find that human responses are more consistent with our framework for task decomposition than alternative normative accounts and are most consistent with a heuristic -- betweenness centrality -- that is justified by our approach. Taken together, our results provide new theoretical insight into the computational principles underlying the intelligent structuring of goal-directed behavior.

David Abel, Mark K. Ho, Anna Harutyunyan · deepmind

Modern reinforcement learning has been conditioned by at least three dogmas. The first is the environment spotlight, which refers to our tendency to focus on modeling environments rather than agents. The second is our treatment of learning as finding the solution to a task, rather than adaptation. The third is the reward hypothesis, which states that all goals and purposes can be well thought of as maximization of a reward signal. These three dogmas shape much of what we think of as the science of reinforcement learning. While each of the dogmas have played an important role in developing the field, it is time we bring them to the surface and reflect on whether they belong as basic ingredients of our scientific paradigm. In order to realize the potential of reinforcement learning as a canonical frame for researching intelligent agents, we suggest that it is time we shed dogmas one and two entirely, and embrace a nuanced approach to the third.

Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho et al.

Natural language is an intuitive and expressive way to communicate reward information to autonomous agents. It encompasses everything from concrete instructions to abstract descriptions of the world. Despite this, natural language is often challenging to learn from: it is difficult for machine learning methods to make appropriate inferences from such a wide range of input. This paper proposes a generalization of reward design as a unifying principle to ground linguistic communication: speakers choose utterances to maximize expected rewards from the listener's future behaviors. We first extend reward design to incorporate reasoning about unknown future states in a linear bandit setting. We then define a speaker model which chooses utterances according to this objective. Simulations show that short-horizon speakers (reasoning primarily about a single, known state) tend to use instructions, while long-horizon speakers (reasoning primarily about unknown, future states) tend to describe the reward function. We then define a pragmatic listener which performs inverse reward design by jointly inferring the speaker's latent horizon and rewards. Our findings suggest that this extension of reward design to linguistic communication, including the notion of a latent speaker horizon, is a promising direction for achieving more robust alignment outcomes from natural language supervision.

Carlos G. Correa, Sophia Sanborn, Mark K. Ho et al.

Human behavior is often assumed to be hierarchically structured, made up of abstract actions that can be decomposed into concrete actions. However, behavior is typically measured as a sequence of actions, which makes it difficult to infer its hierarchical structure. In this paper, we explore how people form hierarchically structured plans, using an experimental paradigm with observable hierarchical representations: participants create programs that produce sequences of actions in a language with explicit hierarchical structure. This task lets us test two well-established principles of human behavior: utility maximization (i.e. using fewer actions) and minimum description length (MDL; i.e. having a shorter program). We find that humans are sensitive to both metrics, but that both accounts fail to predict a qualitative feature of human-created programs, namely that people prefer programs with reuse over and above the predictions of MDL. We formalize this preference for reuse by extending the MDL account into a generative model over programs, modeling hierarchy choice as the induction of a grammar over actions. Our account can explain the preference for reuse and provides better predictions of human behavior, going beyond simple accounts of compressibility to highlight a principle that guides hierarchical planning.

Ruiqi He, Carlos G. Correa, Thomas L. Griffiths et al.

How are people able to plan so efficiently despite limited cognitive resources? We aimed to answer this question by extending an existing model of human task decomposition that can explain a wide range of simple planning problems by adding structure information to the task to facilitate planning in more complex tasks. The extended model was then applied to a more complex planning domain of spatial navigation. Our results suggest that our framework can correctly predict the navigation strategies of the majority of the participants in an online experiment.

Sevan K. Harootonian, Mark K. Ho, Thomas L. Griffiths et al.

How do LLMs decide what to teach next: by reasoning about a learner's knowledge, or by using simpler rules of thumb? We test this in a controlled task previously used to study human teaching strategies. On each trial, a teacher LLM sees a hypothetical learner's trajectory through a reward-annotated directed graph and must reveal a single edge so the learner would choose a better path if they replanned. We run a range of LLMs as simulated teachers and fit their trial-by-trial choices with the same cognitive models used for humans: a Bayes-Optimal teacher that infers which transitions the learner is missing (inverse planning), weaker Bayesian variants, heuristic baselines (e.g., reward based), and non-mentalizing utility models. In a baseline experiment matched to the stimuli presented to human subjects, most LLMs perform well, show little change in strategy over trials, and their graph-by-graph performance is similar to that of humans. Model comparison (BIC) shows that Bayes-Optimal teaching best explains most models' choices. When given a scaffolding intervention, models follow auxiliary inference- or reward-focused prompts, but these scaffolds do not reliably improve later teaching on heuristic-incongruent test graphs and can sometimes reduce performance. Overall, cognitive model fits provide insight into LLM tutoring policies and show that prompt compliance does not guarantee better teaching decisions.

Micah Carroll, Rohin Shah, Mark K. Ho et al.

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be understood by humans. To demonstrate this, we introduce a simple environment that requires challenging coordination, based on the popular game Overcooked, and learn a simple model that mimics human play. We evaluate the performance of agents trained via self-play and population-based training. These agents perform very well when paired with themselves, but when paired with our human model, they are significantly worse than agents designed to play with the human model. An experiment with a planning algorithm yields the same conclusion, though only when the human-aware planner is given the exact human model that it is playing with. A user study with real humans shows this pattern as well, though less strongly. Qualitatively, we find that the gains come from having the agent adapt to the human's gameplay. Given this result, we suggest several approaches for designing agents that learn about humans in order to better coordinate with them. Code is available at https://github.com/HumanCompatibleAI/overcooked_ai.

Sounak Banerjee, Daphne Cornelisse, Deepak Gopinath et al.

People's goal-directed behaviors are influenced by their cognitive biases, and autonomous systems that interact with people should be aware of this. For example, people's attention to objects in their environment will be biased in a way that systematically affects how they perform everyday tasks such as driving to work. Here, building on recent work in computational cognitive science, we formally articulate the attention-aware inverse planning problem, in which the goal is to estimate a person's attentional biases from their actions. We demonstrate how attention-aware inverse planning systematically differs from standard inverse reinforcement learning and how cognitive biases can be inferred from behavior. Finally, we present an approach to attention-aware inverse planning that combines deep reinforcement learning with computational cognitive modeling. We use this approach to infer the attentional strategies of RL agents in real-life driving scenarios selected from the Waymo Open Dataset, demonstrating the scalability of estimating cognitive biases with attention-aware inverse planning.

Dilip Arumugam, Mark K. Ho, Noah D. Goodman et al.

All biological and artificial agents must learn and make decisions given limits on their ability to process information. As such, a general theory of adaptive behavior should be able to account for the complex interactions between an agent's learning history, decisions, and capacity constraints. Recent work in computer science has begun to clarify the principles that shape these dynamics by bridging ideas from reinforcement learning, Bayesian decision-making, and rate-distortion theory. This body of work provides an account of capacity-limited Bayesian reinforcement learning, a unifying normative framework for modeling the effect of processing constraints on learning and action selection. Here, we provide an accessible review of recent algorithms and theoretical results in this setting, paying special attention to how these ideas can be applied to studying questions in the cognitive and behavioral sciences.

David Abel, Will Dabney, Anna Harutyunyan et al.

Reward is the driving force for reinforcement-learning agents. This paper is dedicated to understanding the expressivity of reward as a way to capture tasks that we would want an agent to perform. We frame this study around three new abstract notions of "task" that might be desirable: (1) a set of acceptable behaviors, (2) a partial ordering over behaviors, or (3) a partial ordering over trajectories. Our main results prove that while reward can express many of these tasks, there exist instances of each task type that no Markov reward function can capture. We then provide a set of polynomial-time algorithms that construct a Markov reward function that allows an agent to optimize tasks of each of these three types, and correctly determine when no such reward function exists. We conclude with an empirical study that corroborates and illustrates our theoretical findings.

Mark K. Ho, Thomas L. Griffiths

Those designing autonomous systems that interact with humans will invariably face questions about how humans think and make decisions. Fortunately, computational cognitive science offers insight into human decision-making using tools that will be familiar to those with backgrounds in optimization and control (e.g., probability theory, statistical machine learning, and reinforcement learning). Here, we review some of this work, focusing on how cognitive science can provide forward models of human decision-making and inverse models of how humans think about others' decision-making. We highlight relevant recent developments, including approaches that synthesize blackbox and theory-driven modeling, accounts that recast heuristics and biases as forms of bounded optimality, and models that characterize human theory of mind and communication in decision-theoretic terms. In doing so, we aim to provide readers with a glimpse of the range of frameworks, methodologies, and actionable insights that lie at the intersection of cognitive science and control research.

Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho et al.

Speakers communicate to influence their partner's beliefs and shape their actions. Belief- and action-based objectives have been explored independently in recent computational models, but it has been challenging to explicitly compare or integrate them. Indeed, we find that they are conflated in standard referential communication tasks. To distinguish these accounts, we introduce a new paradigm called signaling bandits, generalizing classic Lewis signaling games to a multi-armed bandit setting where all targets in the context have some relative value. We develop three speaker models: a belief-oriented speaker with a purely informative objective; an action-oriented speaker with an instrumental objective; and a combined speaker which integrates the two by inducing listener beliefs that generally lead to desirable actions. We then present a series of simulations demonstrating that grounding production choices in future listener actions results in relevance effects and flexible uses of nonliteral language. More broadly, our findings suggest that language games based on richer decision problems are a promising avenue for insight into rational communication.

Mark K. Ho, David Abel, Carlos G. Correa et al.

One of the most striking features of human cognition is the capacity to plan. Two aspects of human planning stand out: its efficiency and flexibility. Efficiency is especially impressive because plans must often be made in complex environments, and yet people successfully plan solutions to myriad everyday problems despite having limited cognitive resources. Standard accounts in psychology, economics, and artificial intelligence have suggested human planning succeeds because people have a complete representation of a task and then use heuristics to plan future actions in that representation. However, this approach generally assumes that task representations are fixed. Here, we propose that task representations can be controlled and that such control provides opportunities to quickly simplify problems and more easily reason about them. We propose a computational account of this simplification process and, in a series of pre-registered behavioral experiments, show that it is subject to online cognitive control and that people optimally balance the complexity of a task representation and its utility for planning and acting. These results demonstrate how strategically perceiving and conceiving problems facilitates the effective use of limited cognitive resources.

Theodore R. Sumers, Mark K. Ho, Thomas L. Griffiths

Successful teaching entails a complex interaction between a teacher and a learner. The teacher must select and convey information based on what they think the learner perceives and believes. Teaching always involves misaligned beliefs, but studies of pedagogy often focus on situations where teachers and learners share perceptions. Nonetheless, a teacher and learner may not always experience or attend to the same aspects of the environment. Here, we study how misaligned perceptions influence communication. We hypothesize that the efficacy of different forms of communication depends on the shared perceptual state between teacher and learner. We develop a cooperative teaching game to test whether concrete mediums (demonstrations, or "showing") are more robust than abstract ones (language, or "telling") when the teacher and learner are not perceptually aligned. We find evidence that (1) language-based teaching is more affected by perceptual misalignment, but (2) demonstration-based teaching is less likely to convey nuanced information. We discuss implications for human pedagogy and machine learning.

Theodore R. Sumers, Mark K. Ho, Robert D. Hawkins et al.

We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g., commands). We propose a general framework which does not make this assumption, using aspect-based sentiment analysis to decompose feedback into sentiment about the features of a Markov decision process. We then perform an analogue of inverse reinforcement learning, regressing the sentiment on the features to infer the teacher's latent reward function. To evaluate our approach, we first collect a corpus of teaching behavior in a cooperative task where both teacher and learner are human. We implement three artificial learners: sentiment-based "literal" and "pragmatic" models, and an inference network trained end-to-end to predict latent rewards. We then repeat our initial experiment and pair them with human teachers. All three successfully learn from interactive human feedback. The sentiment models outperform the inference network, with the "pragmatic" model approaching human performance. Our work thus provides insight into the information structure of naturalistic linguistic feedback as well as methods to leverage it for reinforcement learning.

Yun-Shiuan Chuang, Xuezhou Zhang, Yuzhe Ma et al.

Successful teaching requires an assumption of how the learner learns - how the learner uses experiences from the world to update their internal states. We investigate what expectations people have about a learner when they teach them in an online manner using rewards and punishment. We focus on a common reinforcement learning method, Q-learning, and examine what assumptions people have using a behavioral experiment. To do so, we first establish a normative standard, by formulating the problem as a machine teaching optimization problem. To solve the machine teaching optimization problem, we use a deep learning approximation method which simulates learners in the environment and learns to predict how feedback affects the learner's internal states. What do people assume about a learner's learning and discount rates when they teach them an idealized exploration-exploitation task? In a behavioral experiment, we find that people can teach the task to Q-learners in a relatively efficient and effective manner when the learner uses a small value for its discounting rate and a large value for its learning rate. However, they still are suboptimal. We also find that providing people with real-time updates of how possible feedback would affect the Q-learner's internal states weakly helps them teach. Our results reveal how people teach using evaluative feedback and provide guidance for how engineers should design machine agents in a manner that is intuitive for people.

Carlos G. Correa, Mark K. Ho, Fred Callaway et al.

People often plan hierarchically. That is, rather than planning over a monolithic representation of a task, they decompose the task into simpler subtasks and then plan to accomplish those. Although much work explores how people decompose tasks, there is less analysis of why people decompose tasks in the way they do. Here, we address this question by formalizing task decomposition as a resource-rational representation problem. Specifically, we propose that people decompose tasks in a manner that facilitates efficient use of limited cognitive resources given the structure of the environment and their own planning algorithms. Using this model, we replicate several existing findings. Our account provides a normative explanation for how people identify subtasks as well as a framework for studying how people reason, plan, and act using resource-rational representations.

Mark K. Ho, David Abel, Jonathan D. Cohen et al.

Planning is useful. It lets people take actions that have desirable long-term consequences. But, planning is hard. It requires thinking about consequences, which consumes limited computational and cognitive resources. Thus, people should plan their actions, but they should also be smart about how they deploy resources used for planning their actions. Put another way, people should also "plan their plans". Here, we formulate this aspect of planning as a meta-reasoning problem and formalize it in terms of a recursive Bellman objective that incorporates both task rewards and information-theoretic planning costs. Our account makes quantitative predictions about how people should plan and meta-plan as a function of the overall structure of a task, which we test in two experiments with human participants. We find that people's reaction times reflect a planned use of information processing, consistent with our account. This formulation of planning to plan provides new insight into the function of hierarchical planning, state abstraction, and cognitive control in both humans and machines.

Mark K. Ho, Joanna Korman, Thomas L. Griffiths

Speech-acts can have literal meaning as well as pragmatic meaning, but these both involve consequences typically intended by a speaker. Speech-acts can also have unintentional meaning, in which what is conveyed goes above and beyond what was intended. Here, we present a Bayesian analysis of how, to a listener, the meaning of an utterance can significantly differ from a speaker's intended meaning. Our model emphasizes how comprehending the intentional and unintentional meaning of speech-acts requires listeners to engage in sophisticated model-based perspective-taking and reasoning about the history of the state of the world, each other's actions, and each other's observations. To test our model, we have human participants make judgments about vignettes where speakers make utterances that could be interpreted as intentional insults or unintentional faux pas. In elucidating the mechanics of speech-acts with unintentional meanings, our account provides insight into how communication both functions and malfunctions.

Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari et al.

Real world applications often naturally decompose into several sub-tasks. In many settings (e.g., robotics) demonstrations provide a natural way to specify the sub-tasks. However, most methods for learning from demonstrations either do not provide guarantees that the artifacts learned for the sub-tasks can be safely recombined or limit the types of composition available. Motivated by this deficit, we consider the problem of inferring Boolean non-Markovian rewards (also known as logical trace properties or specifications) from demonstrations provided by an agent operating in an uncertain, stochastic environment. Crucially, specifications admit well-defined composition rules that are typically easy to interpret. In this paper, we formulate the specification inference task as a maximum a posteriori (MAP) probability inference problem, apply the principle of maximum entropy to derive an analytic demonstration likelihood model and give an efficient approach to search for the most likely specification in a large candidate pool of specifications. In our experiments, we demonstrate how learning specifications can help avoid common problems that often arise due to ad-hoc reward composition.